Update app.py

app.py

@@ -1,63 +1,35 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-# Update the model name here
-client = InferenceClient(model="nvidia/Llama3-ChatQA-1.5-8B")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+from transformers import pipeline
+from fastapi import FastAPI
+from pydantic import BaseModel
+import uvicorn
+
+# Load the model
+model_name = "nvidia/Llama3-ChatQA-1.5-8B"
+qa_pipeline = pipeline("text-generation", model=model_name)
+
+# FastAPI app
+app = FastAPI()
+
+class Query(BaseModel):
+    inputs: str
+
+@app.post("/predict")
+async def predict(query: Query):
+    response = qa_pipeline(query.inputs, max_length=250)
+    return {"generated_text": response[0]["generated_text"]}
+
+# Gradio app
+def generate_answer(question):
+    response = qa_pipeline(question, max_length=250)
+    return response[0]["generated_text"]
+
+iface = gr.Interface(fn=generate_answer, inputs="text", outputs="text", title="Llama3 ChatQA")
+
+# Mount Gradio app to FastAPI
+@app.get("/")
+async def gradio_app():
+    return gr.mount_gradio_app(app, iface)
 
 if __name__ == "__main__":
-    demo.launch(share=True)  # Ensure share=True to get a public URL
+    uvicorn.run(app, host="0.0.0.0", port=7860)